arXiv subjects

Vittorio Palladino

Publications and source records attributed to Vittorio Palladino.

7 recordsLinked to original sources

arXiv2026

OA-MPPI: Occlusion-Aware Model Predictive Path Integral Control for UAV Flight

Autonomous UAV flight through cluttered and partially unknown environments requires reasoning not only about observed obstacles but also about occluded regions that the sensor cannot observe. We present OA-MPPI, an obstacle- and occlusion-aware extension of Model Predictive Path Integral (MPPI) control for quadrotor flight that accounts for potential moving agents emerging from these regions into the vehicle's path. At every planning step, we extract a 3D occlusion boundary from the online occupancy map and use it to model the regions that hidden agents could reach over the prediction horizon. We penalize trajectories that enter these expanding regions within MPPI rollouts generated using nonlinear quadrotor dynamics and accounting for individual rotor thrust limits. We validate the proposed approach in simulation and hardware flight experiments, with the complete pipeline running onboard the vehicle in real time. Results show increased clearance from occlusion boundaries compared to baseline MPPI in both settings, as well as avoidance of an agent emerging from occlusion in simulation.

cs.RO↗

arXiv2026

DynGhost: Temporally-Modelled Transformer for Dynamic Ghost Imaging with Quantum Detectors

Ghost imaging reconstructs spatial information from a single-pixel bucket detector by correlating structured illumination patterns with scalar intensity measurements. While deep learning approaches have achieved promising results on static scenes, two critical limitations remain unaddressed: existing architectures fail to exploit temporal coherence across frames, leaving dynamic ghost imaging largely unsolved, and they assume additive Gaussian noise models that do not reflect the true Poissonian statistics of real single-photon hardware. We present DynGhost (Dynamic Ghost Imaging Transformer), a transformer architecture that addresses both limitations through alternating spatial and temporal attention blocks. Our quantum-aware training framework, based on physically accurate detector simulations (SNSPDs, SPADs, SiPMs) and Anscombe variance-stabilizing normalization, resolves the distribution shift that causes classical models to fail under realistic hardware constraints. Experiments across multiple benchmarks demonstrate that DynGhost outperforms both traditional reconstruction methods and existing deep learning architectures, with particular gains in dynamic and photon-starved settings.

cs.CV↗

arXiv2026

EnergyLens: Interpretable Closed-Form Energy Models for Multimodal LLM Inference Serving

As large language models span dense, mixture-of-experts, and state-space architectures and are deployed on heterogeneous accelerators under increasingly diverse multimodal workloads, optimising inference energy has become as critical as optimizing latency and throughput. Existing approaches either treat latency as an energy proxy or rely on data-hungry black-box surrogates. Both fail under varying parallelism strategies: latency and energy optima diverge in over 20% of configurations we tested, and black-box surrogates require hundreds of profiling samples to generalize across model families and hardware. We present EnergyLens, which uses symbolic regression as a structure-discovery tool over profiling data to derive a single twelve-parameter closed-form energy model expressed in terms of system properties such as degree of parallelism, batch size, and sequence length. Unlike black-box surrogates, EnergyLens decouples tensor and pipeline parallelism contributions and separates prefill from decode energy, making its predictions physically interpretable and actionable. Fitted from as few as 50 profiling measurements, EnergyLens achieves 88.2% Top-1 configuration selection accuracy across many evaluation scenarios compared to 60.9% for the closest prior analytical baseline, matches the predictive accuracy of ensemble ML methods with 10x fewer profiling samples, and extrapolates reliably to unseen batch sizes and hardware platforms without structural modification, making it a practical, interpretable tool for energy-optimal LLM deployment.

cs.CV↗

arXiv2026

WTHaar-Net: a Hybrid Quantum-Classical Approach

Convolutional neural networks rely on linear filtering operations that can be reformulated efficiently in suitable transform domains. At the same time, advances in quantum computing have shown that certain structured linear transforms can be implemented with shallow quantum circuits, opening the door to hybrid quantum-classical approaches for enhancing deep learning models. In this work, we introduce WTHaar-Net, a convolutional neural network that replaces the Hadamard Transform used in prior hybrid architectures with the Haar Wavelet Transform (HWT). Unlike the Hadamard Transform, the Haar transform provides spatially localized, multi-resolution representations that align more closely with the inductive biases of vision tasks. We show that the HWT admits a quantum realization using structured Hadamard gates, enabling its decomposition into unitary operations suitable for quantum circuits. Experiments on CIFAR-10 and Tiny-ImageNet demonstrate that WTHaar-Net achieves substantial parameter reduction while maintaining competitive accuracy. On Tiny-ImageNet, our approach outperforms both ResNet and Hadamard-based baselines. We validate the quantum implementation on IBM Quantum cloud hardware, demonstrating compatibility with near-term quantum devices.

cs.CV↗

arXiv2019

Future Opportunities in Accelerator-based Neutrino Physics

This document summarizes the conclusions of the Neutrino Town Meeting held at CERN in October 2018 to review the neutrino field at large with the aim of defining a strategy for accelerator-based neutrino physics in Europe. The importance of the field across its many complementary components is stressed. Recommendations are presented regarding the accelerator based neutrino physics, pertinent to the European Strategy for Particle Physics. We address in particular i) the role of CERN and its neutrino platform, ii) the importance of ancillary neutrino cross-section experiments, and iii) the capability of fixed target experiments as well as present and future high energy colliders to search for the possible manifestations of neutrino mass generation mechanisms.

hep-ex↗

arXiv2019

Research and Development for Near Detector Systems Towards Long Term Evolution of Ultra-precise Long-baseline Neutrino Experiments

With the discovery of non-zero value of $θ_{13}$ mixing angle, the next generation of long-baseline neutrino (LBN) experiments offers the possibility of obtaining statistically significant samples of muon and electron neutrinos and anti-neutrinos with large oscillation effects. In this document we intend to highlight the importance of Near Detector facilities in LBN experiments to both constrain the systematic uncertainties affecting oscillation analyses but also to perform, thanks to their close location, measurements of broad benefit for LBN physics goals. A strong European contribution to these efforts is possible.

physics.ins-det↗

arXiv2012

European Strategy for Accelerator-Based Neutrino Physics

Massive neutrinos reveal physics beyond the Standard Model, which could have deep consequences for our understanding of the Universe. Their study should therefore receive the highest level of priority in the European Strategy. The discovery and study of leptonic CP violation and precision studies of the transitions between neutrino flavours require high intensity, high precision, long baseline accelerator neutrino experiments. The community of European neutrino physicists involved in oscillation experiments is strong enough to support a major neutrino long baseline project in Europe, and has an ambitious, competitive and coherent vision to propose. Following the 2006 European Strategy for Particle Physics (ESPP) recommendations, two complementary design studies have been carried out: LAGUNA/LBNO, focused on deep underground detector sites, and EUROnu, focused on high intensity neutrino facilities. LAGUNA LBNO recommends, as first step, a conventional neutrino beam CN2PY from a CERN SPS North Area Neutrino Facility (NANF) aimed at the Pyhasalmi mine in Finland. A sterile neutrino search experiment which could also be situated in the CERN north area has been proposed (ICARUS-NESSIE) using a two detector set-up, allowing a definitive answer to the 20 year old question open by the LSND experiment. EUROnu concluded that a 10 GeV Neutrino Factory, aimed at a magnetized neutrino detector situated, also, at a baseline of around 2200 km (+-30%), would constitute the ultimate neutrino facility; it recommends that the next 5 years be devoted to the R&D, preparatory experiments and implementation study, in view of a proposal before the next ESPP update. The coherence and quality of this program calls for the continuation of neutrino beams at CERN after the CNGS, and for a high priority support from CERN and the member states to the experiments and R&D program.

hep-ex↗